Research On Sustainable Genetic Algorithm

This paper proposed the sustainable evolutionary algorithm-HFC (Hierarchical Fair Competition) model which improves the flaw of standard genetic algorithm. Inspired by the fair competition principle in biologic systems, the HFC model is developed. In the HFC model, the individual are divided into several fitness levels by different fitness and keep evolution going at all fitness levels asynchronously/synchronously. Admission threshold and input buffers are also employed to direct the migration activities and to accommodate migrating individuals between different levels.Transforming the conventional convergent evolutionary computation model into a sustainable search framework,HFC model can not only relieve the severeness of premature convergence, but also maintain the diversity of population significantly. Considering the fact that the HFC model is conceived on the basis of the standard genetic algorithm, there are also inherent flaws on its structure in the HFC model. In order to alleviating this problem, some adaptive mechanism are also used in HFC model. Thus, two kinds of improved HFC algorithm are proposed in this paper.The three kinds of HFC algorithms are static HFC algorithm (SHFC), HFC algorithm with adaptive admission threshold (HFC-nor) and HFC algorithm with inertia item(HFC-adap).The HFC-nor algorithm can adjust the admission thresholds of every grade adaptively; the HFC-ADAP algorithm assures the updating process of threshold value more smoothly.Finally, this paper describes the detailed procedure of three kinds of HFC model-SHFC, HFC-NOR and HFC-ADAP. Experimental results of bin-coded HIFF 128/256 Problem and real-coded De Jong's Functions show that HFC-based algorithms have good diversity amongst population and better solution quality.It also demostrated that HFC-based algorithms have sustainable capability under benchmark testing problems.